{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:17:55Z","timestamp":1771877875631,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":105,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T00:00:00Z","timestamp":1745539200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,26]]},"DOI":"10.1145\/3706598.3713408","type":"proceedings-article","created":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T03:17:03Z","timestamp":1745464623000},"page":"1-31","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Deceptive Explanations by Large Language Models Lead People to Change their Beliefs About Misinformation More Often than Honest Explanations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5225-0077","authenticated-orcid":false,"given":"Valdemar","family":"Danry","sequence":"first","affiliation":[{"name":"MIT Media Lab, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1879-7340","authenticated-orcid":false,"given":"Pat","family":"Pataranutaporn","sequence":"additional","affiliation":[{"name":"MIT Media Lab, Massachusetts Institute of Technology, Boston, Massachusetts, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9029-0157","authenticated-orcid":false,"given":"Matthew","family":"Groh","sequence":"additional","affiliation":[{"name":"Kellogg School of Management, Northwestern, Evanston, Illinois, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5831-5756","authenticated-orcid":false,"given":"Ziv","family":"Epstein","sequence":"additional","affiliation":[{"name":"Stanford Institute for Human-Centered AI, Stanford University, Stanford, California, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,4,25]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5513"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445717"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Dipto Barman Ziyi Guo and Owen Conlan. 2024. The dark side of language models: Exploring the potential of llms in multimedia disinformation generation and dissemination. Machine Learning with Applications (2024) 100545.","DOI":"10.1016\/j.mlwa.2024.100545"},{"key":"e_1_3_3_2_5_2","unstructured":"BBC Newsround. 2023. BBC Newsround. https:\/\/www.bbc.co.uk\/newsround\/66796495. Accessed: 2023-09-01."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Marcel Binz and Eric Schulz. 2023. Using cognitive psychology to understand GPT-3. Proceedings of the National Academy of Sciences 120 6 (2023) e2218523120.","DOI":"10.1073\/pnas.2218523120"},{"key":"e_1_3_3_2_7_2","unstructured":"Tom\u00a0B Brown. 2020. Language models are few-shot learners. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2005.14165 (2020)."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Zana Bu\u00e7inca Maja\u00a0Barbara Malaya and Krzysztof\u00a0Z Gajos. 2021. To trust or to think: cognitive forcing functions can reduce overreliance on AI in AI-assisted decision-making. Proceedings of the ACM on Human-Computer Interaction 5 CSCW1 (2021) 1\u201321.","DOI":"10.1145\/3449287"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Samantha Chan Pat Pataranutaporn Aditya Suri Wazeer Zulfikar Pattie Maes and Elizabeth\u00a0F Loftus. 2024. Conversational AI Powered by Large Language Models Amplifies False Memories in Witness Interviews. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.04681 (2024).","DOI":"10.21428\/cb6ab371.6ae390a8"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Shan Chen Benjamin\u00a0H Kann Michael\u00a0B Foote Hugo\u00a0JWL Aerts Guergana\u00a0K Savova Raymond\u00a0H Mak and Danielle\u00a0S Bitterman. 2023. Use of artificial intelligence chatbots for cancer treatment information. JAMA oncology 9 10 (2023) 1459\u20131462.","DOI":"10.1001\/jamaoncol.2023.2954"},{"key":"e_1_3_3_2_11_2","unstructured":"Roberto Confalonieri Tarek\u00a0R Besold Tillman Weyde Kathleen Creel Tania Lombrozo Shane Mueller and Patrick Shafto. 2019. What makes a good explanation? Cognitive dimensions of explaining intelligent machines. CogSci 2019: Creativity+ Cognition+ Computation (2019)."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"John Cook Peter Ellerton and David Kinkead. 2018. Deconstructing climate misinformation to identify reasoning errors. Environmental Research Letters 13 2 (2018) 024018.","DOI":"10.1088\/1748-9326\/aaa49f"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3384657.3384799"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580672"},{"key":"e_1_3_3_2_15_2","unstructured":"Valdemar\u00a0M Danry. 2023. AI Enhanced Reasoning: Augmenting Human Critical Thinking with AI Systems. Ph.\u00a0D. Dissertation. Massachusetts Institute of Technology."},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Karl de Fine\u00a0Licht and Jenny de Fine\u00a0Licht. 2020. Artificial intelligence transparency and public decision-making: Why explanations are key when trying to produce perceived legitimacy. AI & society 35 (2020) 917\u2013926.","DOI":"10.1007\/s00146-020-00960-w"},{"key":"e_1_3_3_2_17_2","unstructured":"Finale Doshi-Velez and Been Kim. 2017. Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1702.08608 (2017)."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Mengnan Du Ninghao Liu and Xia Hu. 2019. Techniques for interpretable machine learning. Commun. ACM 63 1 (2019) 68\u201377.","DOI":"10.1145\/3359786"},{"key":"e_1_3_3_2_19_2","unstructured":"Esin Durmus and Claire Cardie. 2019. Exploring the role of prior beliefs for argument persuasion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1906.11301 (2019)."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Ullrich\u00a0KH Ecker Stephan Lewandowsky Ee\u00a0Pin Chang and Rekha Pillai. 2014. The effects of subtle misinformation in news headlines. Journal of experimental psychology: applied 20 4 (2014) 323.","DOI":"10.1037\/xap0000028"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445188"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290607.3312787"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Ziv Epstein Antonio\u00a0Alonso Arechar and David Rand. 2023. What label should be applied to content produced by generative AI? (2023).","DOI":"10.31234\/osf.io\/v4mfz"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v16i1.19283"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Ziv Epstein Aaron Hertzmann Investigators of Human\u00a0Creativity Memo Akten Hany Farid Jessica Fjeld Morgan\u00a0R Frank Matthew Groh Laura Herman Neil Leach et\u00a0al. 2023. Art and the science of generative AI. Science 380 6650 (2023) 1110\u20131111.","DOI":"10.1126\/science.adh4451"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376232"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Ziv Epstein Nathaniel Sirlin Antonio Arechar Gordon Pennycook and David Rand. 2023. The social media context interferes with truth discernment. Science Advances 9 9 (2023) eabo6169.","DOI":"10.1126\/sciadv.abo6169"},{"key":"e_1_3_3_2_28_2","unstructured":"FactCheck.org. 2016. FactCheck - Our process. https:\/\/www.factcheck.org\/our-process\/"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511818455"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Valerie\u00a0S Folkes. 1985. Mindlessness or mindfulness: A partial replication and extension of Langer Blank and Chanowitz. Journal of Personality and Social Psychology (1985).","DOI":"10.1037\/\/0022-3514.48.3.600"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Shane Frederick. 2005. Cognitive reflection and decision making. Journal of Economic perspectives 19 4 (2005) 25\u201342.","DOI":"10.1257\/089533005775196732"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/2896377.2901462"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Saadia Gabriel Skyler Hallinan Maarten Sap Pemi Nguyen Franziska Roesner Eunsol Choi and Yejin Choi. 2021. Misinfo Reaction Frames: Reasoning about Readers\u2019 Reactions to News Headlines. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2104.08790 (2021).","DOI":"10.18653\/v1\/2022.acl-long.222"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3490099.3511138"},{"key":"e_1_3_3_2_35_2","unstructured":"Artur\u00a0d\u2019Avila Garcez and Luis\u00a0C Lamb. 2020. Neurosymbolic AI: The 3rd Wave. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2012.05876 (2020)."},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Ga\u00ebl Gendron Qiming Bao Michael Witbrock and Gillian Dobbie. 2023. Large language models are not strong abstract reasoners. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.19555 (2023).","DOI":"10.24963\/ijcai.2024\/693"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Josh\u00a0A Goldstein Jason Chao Shelby Grossman Alex Stamos and Michael Tomz. 2024. How persuasive is AI-generated propaganda? PNAS nexus 3 2 (2024) pgae034.","DOI":"10.1093\/pnasnexus\/pgae034"},{"key":"e_1_3_3_2_38_2","unstructured":"Josh\u00a0A Goldstein Girish Sastry Micah Musser Renee DiResta Matthew Gentzel and Katerina Sedova. 2023. Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigations. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2301.04246 (2023)."},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Lucas Graves. 2017. Anatomy of a fact check: Objective practice and the contested epistemology of fact checking. Communication culture & critique 10 3 (2017) 518\u2013537.","DOI":"10.1111\/cccr.12163"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"crossref","unstructured":"David Gunning Mark Stefik Jaesik Choi Timothy Miller Simone Stumpf and Guang-Zhong Yang. 2019. XAI\u2014Explainable artificial intelligence. Science robotics 4 37 (2019) eaay7120.","DOI":"10.1126\/scirobotics.aay7120"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3650892"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"crossref","unstructured":"Kobi Hackenburg and Helen Margetts. 2024. Evaluating the persuasive influence of political microtargeting with large language models. Proceedings of the National Academy of Sciences 121 24 (2024) e2403116121.","DOI":"10.1073\/pnas.2403116121"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"crossref","unstructured":"Jonathan Haidt. 2001. The emotional dog and its rational tail: a social intuitionist approach to moral judgment. Psychological review 108 4 (2001) 814.","DOI":"10.1037\/\/0033-295X.108.4.814"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5102"},{"key":"e_1_3_3_2_45_2","unstructured":"Jie Huang Xinyun Chen Swaroop Mishra Huaixiu\u00a0Steven Zheng Adams\u00a0Wei Yu Xinying Song and Denny Zhou. 2023. Large language models cannot self-correct reasoning yet. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.01798 (2023)."},{"key":"e_1_3_3_2_46_2","unstructured":"Lujain Ibrahim Saffron Huang Lama Ahmad and Markus Anderljung. 2024. Beyond static AI evaluations: advancing human interaction evaluations for LLM harms and risks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.10632 (2024)."},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581219"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"crossref","unstructured":"Maurice Jakesch Advait Bhat Daniel Buschek Lior Zalmanson and Mor Naaman. 2022. Interacting with Opinionated Language Models Changes Users\u2019 Views. Arxiv Open Access (2022).","DOI":"10.1145\/3544548.3581196"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"crossref","unstructured":"Jinglu Jiang Surinder Kahai and Ming Yang. 2022. Who needs explanation and when? Juggling explainable AI and user epistemic uncertainty. International Journal of Human-Computer Studies 165 (2022) 102839.","DOI":"10.1016\/j.ijhcs.2022.102839"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"crossref","unstructured":"Dominic\u00a0DP Johnson and James\u00a0H Fowler. 2011. The evolution of overconfidence. Nature 477 7364 (2011) 317\u2013320.","DOI":"10.1038\/nature10384"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"crossref","unstructured":"Nicola Jones. 2024. \u2019In awe\u2019: scientists impressed by latest ChatGPT model o1. Nature 634 8033 (2024) 275\u2013276.","DOI":"10.1038\/d41586-024-03169-9"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"crossref","unstructured":"Elise Karinshak Sunny\u00a0Xun Liu Joon\u00a0Sung Park and Jeffrey Hancock. 2023. Working with AI to persuade: Examining a large language model\u2019s ability to generate pro-vaccination messages. Stanford Preprint (2023).","DOI":"10.1145\/3579592"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"crossref","unstructured":"Katarina Kertysova. 2018. Artificial intelligence and disinformation: How AI changes the way disinformation is produced disseminated and can be countered. Security and Human Rights 29 1-4 (2018) 55\u201381.","DOI":"10.1163\/18750230-02901005"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"crossref","unstructured":"Celeste Kidd and Abeba Birhane. 2023. How AI can distort human beliefs. Science 380 6651 (2023) 1222\u20131223.","DOI":"10.1126\/science.adi0248"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581001"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287590"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"crossref","unstructured":"Ellen\u00a0J Langer Arthur Blank and Benzion Chanowitz. 1978. The mindlessness of ostensibly thoughtful action: The role of\" placebic\" information in interpersonal interaction. Journal of personality and social psychology 36 6 (1978) 635.","DOI":"10.1037\/\/0022-3514.36.6.635"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3519711"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"crossref","unstructured":"Jennifer\u00a0S Lerner and Philip\u00a0E Tetlock. 1999. Accounting for the effects of accountability. Psychological bulletin 125 2 (1999) 255.","DOI":"10.1037\/\/0033-2909.125.2.255"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"crossref","unstructured":"Stephan Lewandowsky Ullrich\u00a0KH Ecker Colleen\u00a0M Seifert Norbert Schwarz and John Cook. 2012. Misinformation and its correction: Continued influence and successful debiasing. Psychological science in the public interest 13 3 (2012) 106\u2013131.","DOI":"10.1177\/1529100612451018"},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376590"},{"key":"e_1_3_3_2_62_2","unstructured":"Yi Liu Gelei Deng Zhengzi Xu Yuekang Li Yaowen Zheng Ying Zhang Lida Zhao Tianwei Zhang and Yang Liu. 2023. Jailbreaking chatgpt via prompt engineering: An empirical study. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.13860 (2023)."},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"crossref","unstructured":"Jennifer\u00a0M Logg Julia\u00a0A Minson and Don\u00a0A Moore. 2019. Algorithm appreciation: People prefer algorithmic to human judgment. Organizational Behavior and Human Decision Processes 151 (2019) 90\u2013103.","DOI":"10.1016\/j.obhdp.2018.12.005"},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"crossref","unstructured":"Tania Lombrozo. 2016. Explanatory preferences shape learning and inference. Trends in Cognitive Sciences 20 10 (2016) 748\u2013759.","DOI":"10.1016\/j.tics.2016.08.001"},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"crossref","unstructured":"Roger\u00a0C Mayer James\u00a0H Davis and F\u00a0David Schoorman. 1995. An integrative model of organizational trust. Academy of management review 20 3 (1995) 709\u2013734.","DOI":"10.2307\/258792"},{"key":"e_1_3_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/3563359.3597396"},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"crossref","unstructured":"Stanley Milgram. 1963. Behavioral study of obedience. The Journal of abnormal and social psychology 67 4 (1963) 371.","DOI":"10.1037\/h0040525"},{"key":"e_1_3_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.trustnlp-1.17"},{"key":"e_1_3_3_2_69_2","unstructured":"Shane\u00a0T Mueller Robert\u00a0R Hoffman William Clancey Abigail Emrey and Gary Klein. 2019. Explanation in human-AI systems: A literature meta-review synopsis of key ideas and publications and bibliography for explainable AI. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1902.01876 (2019)."},{"key":"e_1_3_3_2_70_2","doi-asserted-by":"crossref","unstructured":"Elena Musi Myrto Aloumpi Elinor Carmi Simeon Yates and Kay O\u2019Halloran. 2022. Developing fake news immunity: fallacies as misinformation triggers during the pandemic. Online Journal of Communication and Media Technologies 12 3 (2022).","DOI":"10.30935\/ojcmt\/12083"},{"key":"e_1_3_3_2_71_2","unstructured":"Yikang Pan Liangming Pan Wenhu Chen Preslav Nakov Min-Yen Kan and William\u00a0Yang Wang. 2023. On the risk of misinformation pollution with large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.13661 (2023)."},{"key":"e_1_3_3_2_72_2","doi-asserted-by":"crossref","unstructured":"Pat Pataranutaporn Ruby Liu Ed Finn and Pattie Maes. 2023. Influencing human\u2013AI interaction by priming beliefs about AI can increase perceived trustworthiness empathy and effectiveness. Nature Machine Intelligence 5 10 (2023) 1076\u20131086.","DOI":"10.1038\/s42256-023-00720-7"},{"key":"e_1_3_3_2_73_2","doi-asserted-by":"crossref","unstructured":"Gordon Pennycook Tyrone\u00a0D Cannon and David\u00a0G Rand. 2018. Prior exposure increases perceived accuracy of fake news. Journal of experimental psychology: general 147 12 (2018) 1865.","DOI":"10.1037\/xge0000465"},{"key":"e_1_3_3_2_74_2","doi-asserted-by":"crossref","unstructured":"Gordon Pennycook Ziv Epstein Mohsen Mosleh Antonio\u00a0A Arechar Dean Eckles and David\u00a0G Rand. 2021. Shifting attention to accuracy can reduce misinformation online. Nature 592 7855 (2021) 590\u2013595.","DOI":"10.1038\/s41586-021-03344-2"},{"key":"e_1_3_3_2_75_2","doi-asserted-by":"crossref","unstructured":"Gordon Pennycook and David\u00a0G Rand. 2019. Lazy not biased: Susceptibility to partisan fake news is better explained by lack of reasoning than by motivated reasoning. Cognition 188 (2019) 39\u201350.","DOI":"10.1016\/j.cognition.2018.06.011"},{"key":"e_1_3_3_2_76_2","first-page":"646909","volume-title":"Frontiers in Education","author":"Puig Blanca","year":"2021","unstructured":"Blanca Puig, Paloma Blanco-Anaya, and Jorge\u00a0J P\u00e9rez-Maceira. 2021. \u201cFake News\u201d or Real Science? Critical thinking to assess information on COVID-19. In Frontiers in Education , Vol.\u00a06. Frontiers Media SA, 646909."},{"key":"e_1_3_3_2_77_2","doi-asserted-by":"crossref","unstructured":"Leonid Rozenblit and Frank Keil. 2002. The misunderstood limits of folk science: An illusion of explanatory depth. Cognitive science 26 5 (2002) 521\u2013562.","DOI":"10.1207\/s15516709cog2605_1"},{"key":"e_1_3_3_2_78_2","doi-asserted-by":"crossref","unstructured":"Eike Schneiders Tina Seabrooke Joshua Krook Richard Hyde Natalie Leesakul Jeremie Clos and Joel Fischer. 2024. Objection Overruled! Lay People can Distinguish Large Language Models from Lawyers but still Favour Advice from an LLM. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.07871 (2024).","DOI":"10.1145\/3706598.3713470"},{"key":"e_1_3_3_2_79_2","unstructured":"Mrinank Sharma Meg Tong Tomasz Korbak David Duvenaud Amanda Askell Samuel\u00a0R Bowman Newton Cheng Esin Durmus Zac Hatfield-Dodds Scott\u00a0R Johnston et\u00a0al. 2023. Towards understanding sycophancy in language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.13548 (2023)."},{"key":"e_1_3_3_2_80_2","unstructured":"Shruthi Shekar Pat Pataranutaporn Chethan Sarabu Guillermo\u00a0A Cecchi and Pattie Maes. 2024. People over trust AI-generated medical responses and view them to be as valid as doctors despite low accuracy. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.15266 (2024)."},{"key":"e_1_3_3_2_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/3656156.3665126"},{"key":"e_1_3_3_2_82_2","doi-asserted-by":"crossref","unstructured":"Nathaniel Sirlin Ziv Epstein Antonio\u00a0A Arechar and David\u00a0G Rand. 2021. Digital literacy is associated with more discerning accuracy judgments but not sharing intentions. Harvard Kennedy School Misinformation Review (2021).","DOI":"10.37016\/mr-2020-83"},{"key":"e_1_3_3_2_83_2","doi-asserted-by":"crossref","unstructured":"John Sweller. 1988. Cognitive load during problem solving: Effects on learning. Cognitive science 12 2 (1988) 257\u2013285.","DOI":"10.1016\/0364-0213(88)90023-7"},{"key":"e_1_3_3_2_84_2","doi-asserted-by":"crossref","unstructured":"Aba Szollosi and Ben\u00a0R Newell. 2020. People as intuitive scientists: Reconsidering statistical explanations of decision making. Trends in Cognitive Sciences 24 12 (2020) 1008\u20131018.","DOI":"10.1016\/j.tics.2020.09.005"},{"key":"e_1_3_3_2_85_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3648110"},{"key":"e_1_3_3_2_86_2","doi-asserted-by":"crossref","unstructured":"Ben\u00a0M Tappin Chloe Wittenberg Luke\u00a0B Hewitt Adam\u00a0J Berinsky and David\u00a0G Rand. 2023. Quantifying the potential persuasive returns to political microtargeting. Proceedings of the National Academy of Sciences 120 25 (2023) e2216261120.","DOI":"10.1073\/pnas.2216261120"},{"key":"e_1_3_3_2_87_2","unstructured":"Ross Taylor Marcin Kardas Guillem Cucurull Thomas Scialom Anthony Hartshorn Elvis Saravia Andrew Poulton Viktor Kerkez and Robert Stojnic. 2022. Galactica: A large language model for science. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2211.09085 (2022)."},{"key":"e_1_3_3_2_88_2","doi-asserted-by":"crossref","unstructured":"Paul Thagard. 1989. Explanatory coherence. Behavioral and brain sciences 12 3 (1989) 435\u2013467.","DOI":"10.1017\/S0140525X00057046"},{"key":"e_1_3_3_2_89_2","doi-asserted-by":"crossref","unstructured":"Maggie\u00a0E Toplak Richard\u00a0F West and Keith\u00a0E Stanovich. 2014. Assessing miserly information processing: An expansion of the Cognitive Reflection Test. Thinking & Reasoning 20 2 (2014) 147\u2013168.","DOI":"10.1080\/13546783.2013.844729"},{"key":"e_1_3_3_2_90_2","doi-asserted-by":"crossref","unstructured":"Helena Vasconcelos Matthew J\u00f6rke Madeleine Grunde-McLaughlin Tobias Gerstenberg Michael\u00a0S Bernstein and Ranjay Krishna. 2023. Explanations can reduce overreliance on ai systems during decision-making. Proceedings of the ACM on Human-Computer Interaction 7 CSCW1 (2023) 1\u201338.","DOI":"10.1145\/3579605"},{"key":"e_1_3_3_2_91_2","doi-asserted-by":"crossref","unstructured":"Steeven Villa Thomas Kosch Felix Grelka Albrecht Schmidt and Robin Welsch. 2023. The placebo effect of human augmentation: Anticipating cognitive augmentation increases risk-taking behavior. Computers in Human Behavior 146 (2023) 107787.","DOI":"10.1016\/j.chb.2023.107787"},{"key":"e_1_3_3_2_92_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3636304"},{"key":"e_1_3_3_2_93_2","unstructured":"Jan\u00a0G Voelkel Robb Willer et\u00a0al. 2023. Artificial Intelligence Can Persuade Humans on Political Issues. OSF Preprints (2023)."},{"key":"e_1_3_3_2_94_2","doi-asserted-by":"crossref","unstructured":"Soroush Vosoughi Deb Roy and Sinan Aral. 2018. The spread of true and false news online. science 359 6380 (2018) 1146\u20131151.","DOI":"10.1126\/science.aap9559"},{"key":"e_1_3_3_2_95_2","unstructured":"Ivan Vykopal Mat\u00fa\u0161 Pikuliak Ivan Srba Robert Moro Dominik Macko and Maria Bielikova. 2023. Disinformation capabilities of large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.08838 (2023)."},{"key":"e_1_3_3_2_96_2","unstructured":"Laura Weidinger John Mellor Maribeth Rauh Conor Griffin Jonathan Uesato Po-Sen Huang Myra Cheng Mia Glaese Borja Balle Atoosa Kasirzadeh et\u00a0al. 2021. Ethical and social risks of harm from language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2112.04359 (2021)."},{"key":"e_1_3_3_2_97_2","doi-asserted-by":"crossref","unstructured":"Richard\u00a0F West and Keith\u00a0E Stanovich. 1997. The domain specificity and generality of overconfidence: Individual differences in performance estimation bias. Psychonomic Bulletin & Review 4 3 (1997) 387\u2013392.","DOI":"10.3758\/BF03210798"},{"key":"e_1_3_3_2_98_2","unstructured":"Angus\u00a0R Williams Liam Burke-Moore Ryan Sze-Yin Chan Florence\u00a0E Enock Federico Nanni Tvesha Sippy Yi-Ling Chung Evelina Gabasova Kobi Hackenburg and Jonathan Bright. 2024. Large language models can consistently generate high-quality content for election disinformation operations. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.06731 (2024)."},{"key":"e_1_3_3_2_99_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581068"},{"key":"e_1_3_3_2_100_2","doi-asserted-by":"crossref","unstructured":"Yueqi Xie Jingwei Yi Jiawei Shao Justin Curl Lingjuan Lyu Qifeng Chen Xing Xie and Fangzhao Wu. 2023. Defending chatgpt against jailbreak attack via self-reminders. Nature Machine Intelligence 5 12 (2023) 1486\u20131496.","DOI":"10.1038\/s42256-023-00765-8"},{"key":"e_1_3_3_2_101_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32236-6_51"},{"key":"e_1_3_3_2_102_2","doi-asserted-by":"crossref","unstructured":"Jeffrey\u00a0C Zemla Steven Sloman Christos Bechlivanidis and David\u00a0A Lagnado. 2017. Evaluating everyday explanations. Psychonomic bulletin & review 24 (2017) 1488\u20131500.","DOI":"10.3758\/s13423-017-1258-z"},{"key":"e_1_3_3_2_103_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11564"},{"key":"e_1_3_3_2_104_2","doi-asserted-by":"crossref","unstructured":"Haiyan Zhao Hanjie Chen Fan Yang Ninghao Liu Huiqi Deng Hengyi Cai Shuaiqiang Wang Dawei Yin and Mengnan Du. 2024. Explainability for large language models: A survey. ACM Transactions on Intelligent Systems and Technology 15 2 (2024) 1\u201338.","DOI":"10.1145\/3639372"},{"key":"e_1_3_3_2_105_2","first-page":"375","volume-title":"International Workshop on Extending Explainable AI Beyond Deep Models and Classifiers","author":"Zhou Jianlong","year":"2020","unstructured":"Jianlong Zhou, Fang Chen, and Andreas Holzinger. 2020. Towards explainability for AI fairness. In International Workshop on Extending Explainable AI Beyond Deep Models and Classifiers. Springer, 375\u2013386."},{"key":"e_1_3_3_2_106_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581318"}],"event":{"name":"CHI 2025: CHI Conference on Human Factors in Computing Systems","location":"Yokohama Japan","acronym":"CHI '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706598.3713408","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3706598.3713408","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T04:54:51Z","timestamp":1751604891000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706598.3713408"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,25]]},"references-count":105,"alternative-id":["10.1145\/3706598.3713408","10.1145\/3706598"],"URL":"https:\/\/doi.org\/10.1145\/3706598.3713408","relation":{},"subject":[],"published":{"date-parts":[[2025,4,25]]},"assertion":[{"value":"2025-04-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}